Using Minimum Quantization Error chart for the monitoring of process states in multivariate manufacturing processes

The need for multivariate statistical process control (MSPC) becomes more important as several variables should be monitored simultaneously. MSPC is implemented using a variety of techniques including neural networks (NNs). NNs have excellent noise tolerance in real time, requiring no hypothesis on statistical distribution of monitored processes. This feature makes NNs promising tools used for monitoring process changes. However, major NNs applied in SPC are based on supervised learning, which limits their wide applications. In the paper, a Self-Organizing Map (SOM)-based process monitoring approach is proposed for enhancing the monitoring of manufacturing processes. It is capable to provide a comprehensible and quantitative assessment value for current process state, which is achieved by the Minimum Quantization Error (MQE) calculation. Based on these MQE values over time series, an MQE chart is developed for monitoring process changes. The performance of MQE chart is analyzed in a bivariate process under the assumption that the predictable abnormal patterns are not available. The performance of MQE is further evaluated in a semiconductor batch manufacturing process. The experimental results indicate that MQE charts can become an effective monitoring and analysis tool for MSPC.